Multimodal biometric systems have been subject of study in recent decades, theirunique characteristic of Anti spoofing and liveness detection plus ability to deal withaudio noise made them technology candidates for improving current systems such asvoice recognition, verification and identification systems.In this work we studied feasibility of incorporating audio-visual voice recognitionsystem for dealing with audio noise in the truck cab environment. Speech recognitionsystems suffer from excessive noise from the engine and road traffic and cars stereosystem. To deal with this noise different techniques including active and passive noisecancelling have been studied.Our results showed that although audio-only systems are performing better in noisefree environment their performance drops significantly by increase in the level of noisein truck cabins, which by contrast does not affect the performance of visual features.Final fused system comprising both visual and audio cues, proved to be superior toboth audio-only and video-only systems.

In this thesis, 3D animation of human facial expressions and lip motion and their synchronization with a Turkish Speech engine using JAVA programming language, JAVA3D API and Java Speech API, is analyzed. A three-dimensional animation model for simulating Turkish lip motion and facial expressions is developed. In addition to lip motion, synchronization with a Turkish speech engine is achieved. The output of the study is facial expressions and Turkish lip motion synchronized with Turkish speech, where the input is Turkish text in Java Speech Markup Language (JSML) format, also indicating expressions. Unlike many other languages, in Turkish, words are easily broken up into syllables. This property of Turkish Language lets us use a simple method to map letters to Turkish visual phonemes. In this method, totally 37 face models are used to represent the Turkish visual phonemes and these letters are mapped to 3D facial models considering the syllable structures. The animation is created using JAVA3D API. 3D facial models corresponding to different lip positions of the same person are morphed to each other to construct the animation. Moreover, simulations of human facial expressions of emotions are created within the animation. Expression weight parameter, which states the weight of the given expression, is introduced. The synchronization of lip motion with Turkish speech is achieved via CloudGarden&reg / &rsquo / s Java Speech API interface. As a final point a virtual Turkish speaker with facial expression of emotions is created for JAVA3D animation.